The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the lack of input isolation. Ingestion points: User-provided requirements are interpolated via the $ARGUMENTS variable in SKILL.md. Boundary markers: Absent. The user input is placed directly under the 'Input' header without delimiters to distinguish it from instructional text. Capability inventory: The agent is instructed to perform landscape analysis and technology evaluations, which typically involve search and web browsing tools. Sanitization: No sanitization or validation of the $ARGUMENTS content is performed.

research